作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2023, Vol. 49 ›› Issue (5): 215-222,230. doi: 10.19678/j.issn.1000-3428.0065295

• 移动互联与通信技术 • 上一篇    下一篇

基于ANN的能量采集无线传感器网络中继选择策略

区展华, 李翠然, 杨茜   

  1. 兰州交通大学 电子与信息工程学院, 兰州 730070
  • 收稿日期:2022-07-20 修回日期:2022-10-08 发布日期:2022-11-03
  • 作者简介:区展华(1996-),男,硕士研究生,主研方向为无线传感器网络;李翠然(通信作者),教授、博士、博士生导师;杨
  • 基金资助:
    国家自然科学基金(62161016);甘肃省科技计划项目(20JR10RA273)。

Relay Selection Strategy for Energy Harvesting Wireless Sensor Network Based on ANN

OU Zhanhua, LI Cuiran, YANG Qian   

  1. School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
  • Received:2022-07-20 Revised:2022-10-08 Published:2022-11-03

摘要: 能量采集无线传感器网络(EH-WSN)中继节点的能量补给来源与选择算法是制约网络生命周期的关键因素。为提升EH-WSN可再生能源利用率与中继选择效率,引入配有太阳能电池板与电网供能的能量节点(EN),采用解码转发中继协议与改进的功率分割接收机传输模型,构建多中继EH-WSN协同通信模型。基于二维线性相控阵天线实现EN对中继节点的定向无线能量补给,根据EN能量的不同来源动态调整充能策略,提出最大化网络生命周期下的优化中继选择算法。建立基于人工神经网络(ANN)的中继选择模型,结合反向传播算法与交叉熵函数对模型结果进行修正。仿真结果表明:采用EH-WSN优化中继选择算法的网络生命周期相比于无线携能传输(SWIPT)的WSN增长62%,可再生能源利用率单天最高可达21%;基于ANN模型的中继选择结果准确率可达90%、选择效率提高92%,相比于具有遍历性的EH-WSN优化中继选择算法计算复杂度更低、实时性更高。

关键词: 能量采集无线传感器网络, 功率分割, 中继选择, 太阳能采集, 人工神经网络

Abstract: The energy supply source and Relay Node(RN) selection algorithm of an Energy Harvesting Wireless Sensor Network(EH-WSN) are key factors restricting the network life cycle.In this study,an Energy Node(EN),equipped with solar panels and power grids,is added to the EH-WSN to improve its renewable energy utilization and relay selection efficiency.The multi-relay cooperative communication model of EH-WSN is constructed using the Decode-and-Forward(DF) relay protocol and an improved power split receiver structure.The directional energy supply from the EN to RN is realized using two-dimensional linear phased-array antennas.According to the different energy sources of the EN,the charging strategy is dynamically adjusted,and an optimal relay selection algorithm is proposed to maximize the network life cycle.Simultaneously,a relay selection model based on an Artificial Neural Network(ANN) is established; the relay selection model uses the back-propagation algorithm and cross-entropy function to correct the model structure. The simulation results show that the network life cycle using the EH-WSN optimized relay selection algorithm is 62% longer than that of a Simultaneous Wireless Information and Power Transfer-based Wireless Sensor Network(SWIPT-WSN),and the renewable energy utilization rate can reach a maximum of 21% per day.The accuracy of the relay selection based on the ANN model is up to 90%,and the selection efficiency is improved by 92%.Compared with the ergodic EH-WSN optimized relay selection algorithm,the proposed strategy based on an ANN has low computational complexity and good real-time performance.

Key words: Energy Harvesting Wireless Sensor Network(EH-WSN), power split, relay selection, solar energy harvesting, Artificial Neural Network(ANN)

中图分类号: